{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T12:24:38Z","timestamp":1777379078834,"version":"3.51.4"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:00:00Z","timestamp":1775779200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Array"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.array.2026.100818","type":"journal-article","created":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T08:38:30Z","timestamp":1775896710000},"page":"100818","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Benchmark analysis of deep learning algorithms for edge-based robotic applications"],"prefix":"10.1016","volume":"30","author":[{"given":"Quang Nhat","family":"Nguyen Le","sequence":"first","affiliation":[]},{"given":"Mamen Thomas","family":"Chembakasseril","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9441-8843","authenticated-orcid":false,"given":"Ronny","family":"Hartanto","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.array.2026.100818_b1","doi-asserted-by":"crossref","unstructured":"Lang AH, Vora S, Caesar H, Zhou L, Yang J, Beijbom O. Pointpillars: Fast encoders for object detection from point clouds. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019, p. 12697\u2013705.","DOI":"10.1109\/CVPR.2019.01298"},{"issue":"3","key":"10.1016\/j.array.2026.100818_b2","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","article-title":"Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges","volume":"22","author":"Feng","year":"2020","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"1","key":"10.1016\/j.array.2026.100818_b3","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1109\/TITS.2020.3013234","article-title":"Multimodal end-to-end autonomous driving","volume":"23","author":"Xiao","year":"2020","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"6","key":"10.1016\/j.array.2026.100818_b4","doi-asserted-by":"crossref","first-page":"5068","DOI":"10.1109\/TITS.2020.3046646","article-title":"Interpretable end-to-end urban autonomous driving with latent deep reinforcement learning","volume":"23","author":"Chen","year":"2021","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"4","key":"10.1016\/j.array.2026.100818_b5","doi-asserted-by":"crossref","DOI":"10.2196\/27850","article-title":"Chatbot for health care and oncology applications using artificial intelligence and machine learning: systematic review","volume":"7","author":"Xu","year":"2021","journal-title":"JMIR Cancer"},{"key":"10.1016\/j.array.2026.100818_b6","series-title":"Artificial intelligence in medicine","first-page":"1","article-title":"Artificial intelligence in radiotherapy and patient care","author":"Chow","year":"2021"},{"issue":"10","key":"10.1016\/j.array.2026.100818_b7","doi-asserted-by":"crossref","DOI":"10.2196\/20346","article-title":"The effectiveness of artificial intelligence conversational agents in health care: systematic review","volume":"22","author":"Milne-Ives","year":"2020","journal-title":"J Med Internet Res"},{"key":"10.1016\/j.array.2026.100818_b8","doi-asserted-by":"crossref","first-page":"70","DOI":"10.58496\/BJN\/2025\/006","article-title":"Artificial intelligence for medical diagnostics in IoT-based healthcare networks: Foundations and future trends","volume":"2025","author":"Al-Hassani","year":"2025","journal-title":"Babylon J Netw"},{"key":"10.1016\/j.array.2026.100818_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.114060","article-title":"Machine learning and data mining in manufacturing","volume":"166","author":"Dogan","year":"2021","journal-title":"Expert Syst Appl"},{"key":"10.1016\/j.array.2026.100818_b10","article-title":"Machine learning in additive manufacturing: State-of-the-art and perspectives","volume":"36","author":"Wang","year":"2020","journal-title":"Addit Manuf"},{"issue":"1","key":"10.1016\/j.array.2026.100818_b11","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s10845-022-02029-5","article-title":"Machine learning techniques in additive manufacturing: a state of the art review on design, processes and production control","volume":"34","author":"Kumar","year":"2023","journal-title":"J Intell Manuf"},{"key":"10.1016\/j.array.2026.100818_b12","series-title":"A survey of large language models","author":"Zhao","year":"2023"},{"key":"10.1016\/j.array.2026.100818_b13","series-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"10.1016\/j.array.2026.100818_b14","series-title":"Video generation models as world simulators \u2014 openai.com","year":"2024"},{"issue":"2","key":"10.1016\/j.array.2026.100818_b15","doi-asserted-by":"crossref","first-page":"1165","DOI":"10.1177\/03611981221110566","article-title":"Robotic competitions to design future transport systems: The case of JRC AUTOTRAC 2020","volume":"2677","author":"Ciuffo","year":"2023","journal-title":"Transp Res Rec"},{"key":"10.1016\/j.array.2026.100818_b16","doi-asserted-by":"crossref","first-page":"42","DOI":"10.58496\/MJAIH\/2024\/007","article-title":"Exploring deep learning methods used in the medical device sector","volume":"2024","author":"Kayusi","year":"2024","journal-title":"Mesopotamian J Artif Intell Heal"},{"key":"10.1016\/j.array.2026.100818_b17","doi-asserted-by":"crossref","first-page":"64270","DOI":"10.1109\/ACCESS.2018.2877890","article-title":"Benchmark analysis of representative deep neural network architectures","volume":"6","author":"Bianco","year":"2018","journal-title":"IEEE Access"},{"key":"10.1016\/j.array.2026.100818_b18","doi-asserted-by":"crossref","unstructured":"Lu Z, Rallapalli S, Chan K, La Porta T. Modeling the resource requirements of convolutional neural networks on mobile devices. In: Proceedings of the 25th ACM international conference on multimedia. 2017, p. 1663\u201371.","DOI":"10.1145\/3123266.3123389"},{"key":"10.1016\/j.array.2026.100818_b19","series-title":"2020 IEEE international conference on big data and smart computing (BigComp)","first-page":"117","article-title":"Benchmarking gpu-accelerated edge devices","author":"Jo","year":"2020"},{"issue":"8","key":"10.1016\/j.array.2026.100818_b20","doi-asserted-by":"crossref","first-page":"3734","DOI":"10.3390\/app12083734","article-title":"A deep learning framework performance evaluation to use YOLO in nvidia jetson platform","volume":"12","author":"Shin","year":"2022","journal-title":"Appl Sci","ISSN":"https:\/\/id.crossref.org\/issn\/2076-3417","issn-type":"print"},{"key":"10.1016\/j.array.2026.100818_b21","series-title":"2020 IEEE international conference on big data and smart computing (BigComp)","first-page":"477","article-title":"Benchmarking jetson platform for 3D point-cloud and hyper-spectral image classification","author":"Ullah","year":"2020"},{"key":"10.1016\/j.array.2026.100818_b22","series-title":"Deep learning on edge TPUs","author":"Sun","year":"2021"},{"key":"10.1016\/j.array.2026.100818_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107298","article-title":"Energy efficiency in edge TPU vs. embedded GPU for computer-aided medical imaging segmentation and classification","volume":"127","author":"Rodr\u00edguez Corral","year":"2024","journal-title":"Eng Appl Artif Intell","ISSN":"https:\/\/id.crossref.org\/issn\/0952-1976","issn-type":"print"},{"key":"10.1016\/j.array.2026.100818_b24","series-title":"2021 5th international conference on computing methodologies and communication","first-page":"638","article-title":"Multi-functional personal assistant robot using raspberry pi and coral accelerator","author":"Abraham","year":"2021"},{"key":"10.1016\/j.array.2026.100818_b25","series-title":"2020 IEEE region 10 symposium","first-page":"186","article-title":"Assistive technology for visually impaired using tensor flow object detection in raspberry pi and coral USB accelerator","author":"Ghosh","year":"2020"},{"key":"10.1016\/j.array.2026.100818_b26","doi-asserted-by":"crossref","unstructured":"Antonini M, Vu TH, Min C, Montanari A, Mathur A, Kawsar F. Resource characterisation of personal-scale sensing models on edge accelerators. In: Proceedings of the first international workshop on challenges in artificial intelligence and machine learning for internet of things. 2019, p. 49\u201355.","DOI":"10.1145\/3363347.3363363"},{"key":"10.1016\/j.array.2026.100818_b27","series-title":"KI 2020: advances in artificial intelligence: 43rd german conference on AI, Bamberg, Germany, September 21\u201325, 2020, proceedings 43","first-page":"320","article-title":"Evaluation of deep learning accelerators for object detection at the edge","author":"Puchtler","year":"2020"},{"key":"10.1016\/j.array.2026.100818_b28","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/j.procs.2022.09.025","article-title":"Object detection at the edge: Off-the-shelf deep learning capable devices and accelerators","volume":"205","author":"Galliera","year":"2022","journal-title":"Proc Comput Sci"},{"key":"10.1016\/j.array.2026.100818_b29","series-title":"2020 international congress on human-computer interaction, optimization and robotic applications","first-page":"1","article-title":"Benchmark analysis of jetson TX2, jetson nano and raspberry PI using deep-CNN","author":"S\u00fczen","year":"2020"},{"key":"10.1016\/j.array.2026.100818_b30","series-title":"European conference on computer vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.array.2026.100818_b31","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.array.2026.100818_b32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.70470\/KHWARIZMIA\/2023\/010","article-title":"Efficient hardware acceleration techniques for deep learning on edge devices: A comprehensive performance analysis","volume":"2023","author":"Burhanuddin","year":"2023","journal-title":"KHWARIZMIA"},{"key":"10.1016\/j.array.2026.100818_b33","series-title":"Human modelling and pose estimation overview","author":"Knap","year":"2024"},{"issue":"8","key":"10.1016\/j.array.2026.100818_b34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3469029","article-title":"Machine learning at the network edge: A survey","volume":"54","author":"Murshed","year":"2021","journal-title":"ACM Comput Surv"},{"key":"10.1016\/j.array.2026.100818_b35","doi-asserted-by":"crossref","first-page":"5113","DOI":"10.1007\/s10462-020-09816-7","article-title":"A comprehensive survey on model compression and acceleration","volume":"53","author":"Choudhary","year":"2020","journal-title":"Artif Intell Rev"},{"issue":"3","key":"10.1016\/j.array.2026.100818_b36","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1587\/transinf.2020EDP7160","article-title":"Benchmarking modern edge devices for ai applications","volume":"104","author":"Kang","year":"2021","journal-title":"IEICE Trans Inf Syst"},{"key":"10.1016\/j.array.2026.100818_b37","series-title":"General-purpose graphics processor architectures","author":"Aamodt","year":"2018"},{"key":"10.1016\/j.array.2026.100818_b38","series-title":"Google supercharges machine learning tasks with TPU custom chip","author":"Jouppi","year":"2016"},{"key":"10.1016\/j.array.2026.100818_b39","doi-asserted-by":"crossref","first-page":"7823","DOI":"10.1109\/ACCESS.2018.2890150","article-title":"FPGA-based accelerators of deep learning networks for learning and classification: A review","volume":"7","author":"Shawahna","year":"2018","journal-title":"IEEE Access"},{"key":"10.1016\/j.array.2026.100818_b40","doi-asserted-by":"crossref","DOI":"10.1016\/j.micpro.2022.104441","article-title":"Review of ASIC accelerators for deep neural network","volume":"89","author":"Machupalli","year":"2022","journal-title":"Microprocess Microsyst"},{"key":"10.1016\/j.array.2026.100818_b41","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.array.2026.100818_b42","series-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"10.1016\/j.array.2026.100818_b43","series-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020"},{"key":"10.1016\/j.array.2026.100818_b44","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Bochkovskiy A, Liao H-YM. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2023, p. 7464\u201375.","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"10.1016\/j.array.2026.100818_b45","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1016\/j.procs.2022.01.135","article-title":"A review of yolo algorithm developments","volume":"199","author":"Jiang","year":"2022","journal-title":"Proc Comput Sci"},{"key":"10.1016\/j.array.2026.100818_b46","series-title":"Computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, the Netherlands, October 11\u201314, 2016, proceedings, Part I 14","first-page":"21","article-title":"Ssd: Single shot multibox detector","author":"Liu","year":"2016"},{"key":"10.1016\/j.array.2026.100818_b47","series-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.array.2026.100818_b48","series-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"10.1016\/j.array.2026.100818_b49","series-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","author":"Chen","year":"2014"},{"key":"10.1016\/j.array.2026.100818_b50","series-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"10.1016\/j.array.2026.100818_b51","series-title":"Objects as points","author":"Zhou","year":"2019"},{"key":"10.1016\/j.array.2026.100818_b52","series-title":"BlazeFace: Sub-millisecond neural face detection on mobile GPUs","author":"Bazarevsky","year":"2019"},{"key":"10.1016\/j.array.2026.100818_b53","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C. Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, p. 4510\u201320.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"10.1016\/j.array.2026.100818_b54","series-title":"Dynamic voltage and frequency scaling","author":"Arm Architecture","year":"2023"},{"key":"10.1016\/j.array.2026.100818_b55","series-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023"},{"key":"10.1016\/j.array.2026.100818_b56","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.array.2026.100818_b57","series-title":"European conference on computer vision","first-page":"304","article-title":"MM1: methods, analysis and insights from multimodal LLM pre-training","author":"McKinzie","year":"2024"},{"key":"10.1016\/j.array.2026.100818_b58","series-title":"Llama 3.2: Revolutionizing edge AI and vision with open, customizable models \u2014 ai.meta.com","year":"2024"},{"key":"10.1016\/j.array.2026.100818_b59","series-title":"Field-programmable gate array architecture for deep learning: Survey and future directions","author":"Boutros","year":"2024"}],"container-title":["Array"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2590005626001414?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2590005626001414?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T09:13:08Z","timestamp":1777367588000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2590005626001414"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":59,"alternative-id":["S2590005626001414"],"URL":"https:\/\/doi.org\/10.1016\/j.array.2026.100818","relation":{},"ISSN":["2590-0056"],"issn-type":[{"value":"2590-0056","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Benchmark analysis of deep learning algorithms for edge-based robotic applications","name":"articletitle","label":"Article Title"},{"value":"Array","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.array.2026.100818","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"100818"}}